/* Load the samples from a plain text file with the specified format. */
data *feas_load(char *filename,workers *pool){
data *feas=(data*)calloc(1,sizeof(data));
loader *t=(loader*)calloc(1,sizeof(loader));
t->s=t->d=t->c=t->point=t->next=0,t->header=2,t->dec=t->sign=1;
t->feas=feas,t->buff=NULL; number i,r;
gzFile f=gzopen(filename,"rb"); /* Read the file using zlib library. */
if(!f)fprintf(stderr,"Error: Not %s feature file found.\n",filename),exit(1);
while(!gzeof(f)){
char *buff=(char*)calloc(BUFFER_SIZE,sizeof(char));
r=gzread(f,buff,BUFFER_SIZE); /* Read the buffer and do asynchronous load. */
if(t->buff!=NULL){
workers_waitall(pool);
free(t->buff);
}
t->buff=buff,t->r=r;
workers_addtask(pool,thread_loader,(void*)t);
}
workers_waitall(pool);
gzclose(f); free(t->buff); free(t);
for(i=0;i<feas->dimension;i++){ /* Compute the mean and variance of the data. */
feas->mean[i]/=feas->samples;
feas->variance[i]=(feas->variance[i]/feas->samples)-(feas->mean[i]*feas->mean[i]);
if(feas->variance[i]<0.000001)feas->variance[i]=0.000001;
}
return feas;
}
/* Detailed Gaussian Mixture classifier using a Viterbi aproximation. */
decimal gmm_classify(char *filename,data *feas,gmm *gmix,gmm *gworld,workers *pool){
number i,n=workers_number(pool),inc=feas->samples/n; decimal result=0;
workers_mutex *mutex=workers_mutex_create();
classifier *t=(classifier*)calloc(n,sizeof(classifier));
number *flag=(number*)calloc(1,sizeof(number));
FILE *f=fopen(filename,"w");
if(!f)fprintf(stderr,"Error: Can not write to %s file.\n",filename),exit(1);
fprintf(f,"{\n\t\"samples\": %i,\n\t\"classes\": %i,",feas->samples,gmix->num);
fprintf(f,"\n\t\"samples_results\": [ ");
for(i=0;i<gmix->num;i++)
gmix->mix[i]._cfreq=0;
for(i=0;i<n;i++){ /* Set and launch the parallel classify. */
t[i].feas=feas,t[i].gmix=gmix,t[i].gworld=gworld,t[i].ini=i*inc,t[i].mutex=mutex;
t[i].end=(i==n-1)?(feas->samples):((i+1)*inc),t[i].f=f,t[i].flag=flag;
workers_addtask(pool,thread_classifier,(void*)&t[i]);
}
workers_waitall(pool); /* Wait to the end of the parallel classify. */
for(i=0;i<n;i++)
result+=t[i].result;
workers_mutex_delete(mutex);
fprintf(f,"\n\t],\n\t\"mixture_occupation\": [ %i",gmix->mix[0]._cfreq);
for(i=1;i<gmix->num;i++)
fprintf(f,", %i",gmix->mix[i]._cfreq);
fprintf(f," ],\n\t\"global_score\": %.10f\n}",result);
fclose(f); free(t); free(flag);
return result/feas->samples;
}
/* Perform one iteration of the EM algorithm with the data and the mixture indicated. */
decimal gmm_EMtrain(data *feas,gmm *gmix,workers *pool){
number m,i,inc,n=workers_number(pool); decimal tz,x;
workers_mutex *mutex=workers_mutex_create();
trainer *t=(trainer*)calloc(n,sizeof(trainer));
/* Calculate expected value and accumulate the counts (E Step). */
gmm_init_classifier(gmix);
for(m=0;m<gmix->num;m++)
gmix->mix[m]._cfreq=0;
inc=feas->samples/n;
for(i=0;i<n;i++){ /* Set and launch the parallel training. */
t[i].feas=feas,t[i].gmix=gmix,t[i].mutex=mutex,t[i].ini=i*inc;
t[i].end=(i==n-1)?(feas->samples):((i+1)*inc);
workers_addtask(pool,thread_trainer,(void*)&t[i]);
}
workers_waitall(pool);
workers_mutex_delete(mutex);
/* Estimate the new parameters of the Gaussian Mixture (M Step). */
for(m=0;m<gmix->num;m++){
gmix->mix[m].prior=log((tz=gmix->mix[m]._z)/feas->samples);
for(i=0;i<gmix->dimension;i++){
gmix->mix[m].mean[i]=(x=gmix->mix[m]._mean[i]/tz);
gmix->mix[m].dcov[i]=(gmix->mix[m]._dcov[i]/tz)-(x*x);
if(gmix->mix[m].dcov[i]<gmix->mcov[i]) /* Smoothing covariances. */
gmix->mix[m].dcov[i]=gmix->mcov[i];
}
}
free(t);
return gmix->llh/feas->samples;
}
/* Efficient Gaussian Mixture classifier using a Viterbi aproximation. */
decimal gmm_simple_classify(data *feas,gmm *gmix,gmm *gworld,workers *pool){
number i,n=workers_number(pool),inc=feas->samples/n; decimal result=0;
classifier *t=(classifier*)calloc(n,sizeof(classifier));
for(i=0;i<n;i++){ /* Set and launch the parallel classify. */
t[i].feas=feas,t[i].gmix=gmix,t[i].gworld=gworld,t[i].ini=i*inc;
t[i].end=(i==n-1)?(feas->samples):((i+1)*inc);
workers_addtask(pool,thread_simple_classifier,(void*)&t[i]);
}
workers_waitall(pool); /* Wait to the end of the parallel classify. */
for(i=0;i<n;i++)
result+=t[i].result;
free(t);
return (result*0.5)/feas->samples;
}
